Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/emasoft/claude-plugins-validation/cpv-batch-caching-auditnpx skills add Emasoft/claude-plugins-validation --skill cpv-batch-caching-auditgit clone --depth 1 https://github.com/Emasoft/claude-plugins-validationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/emasoft/claude-plugins-validation/cpv-batch-caching-audit)<a href="https://agentmods.dev/skills/emasoft/claude-plugins-validation/cpv-batch-caching-audit"><img src="https://agentmods.dev/badge/skills/emasoft/claude-plugins-validation/cpv-batch-caching-audit.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00093 | $0.00957 |
| Opus 5 | $0.00046 | $0.00478 |
| Sonnet 5 | $0.00019 | $0.00191 |
| Haiku 4.5 | $0.00009 | $0.00096 |
Grade A, and why
cpv-batch-caching-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cpv-batch-caching-audit
Overview
Read-only parallel cache audit. Runs Phase 1 (Audit) of the
cpv-cache-optimizer-agent workflow across every plugin in the user's
input spec — detecting the seven documented prompt-cache invalidation
patterns (CA-01..CA-07) per plugin without applying fixes. Apply
fixes later with /cpv-batch-caching-optimize (which uses the same
input grammar).
Same input grammar and dispatch shape as
cpv-batch-validate. The
orchestrator body lives in this plugin's
commands/cpv-batch-caching-audit.md slash-command file.
Prerequisites
claude-plugins-validationplugin installed (provides thecpv-cache-optimizer-agent, the universal input resolver, and the cache validator).- For URL inputs:
giton PATH and network access togithub.com. - Read access to every plugin's tree — cache findings include references to specific lines in SKILL.md, agent.md, CLAUDE.md, etc.
Inputs
See the cpv-batch-validate input table — every shape is supported identically.
Instructions
- Confirm the user wants AUDIT-ONLY. If they want to APPLY fixes,
route to
cpv-batch-caching-optimize. - Invoke the slash command body:
/cpv-batch-caching-audit <user's spec> [--max-parallel N] - Each agent runs Phase 1 only (no Phase 2 fix, no Phase 3 re-validate, no Phase 4 broader refactor).
- The user gets the final status table + a one-line summary
(
DONE: plugins=N clean=X findings=Y warning-only=Z). - If any plugin has findings, suggest
/cpv-batch-caching-optimize <same spec>.
Output
- Unicode-bordered status table (one row per plugin).
- One-line DONE summary.
- Per-plugin cache-audit reports under
$MAIN_ROOT/reports/validate_cache/<ts±tz>-<plugin>.md. - Per-plugin status JSONs under
<session_dir>/plugin-<index>.status.json.
Token contract
Same as cpv-batch-validate.
Error Handling
| Condition | Behaviour |
|---|---|
| Empty input | Resolver raises; orchestrator surfaces and stops. |
| Zero-plugin resolve | "Nothing to cache-audit. ✓" + stop. |
| Plugin tree unreadable | Per-plugin status JSON shows failed with the I/O error in notes. |
| One agent fails | Failed plugin gets failed label; others complete normally. |
| Network failure during URL clone | Resolver raises with a remediation message; no partial batch. |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 96 lines · 93 tokens per session scan A 2174afd0d766
cpv-batch-caching-audit is a skill published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 957 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.